Cory Shain


SentSpace: Large-Scale Benchmarking and Evaluation of Text using Cognitively Motivated Lexical, Syntactic, and Semantic Features
Greta Tuckute | Aalok Sathe | Mingye Wang | Harley Yoder | Cory Shain | Evelina Fedorenko
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations

SentSpace is a modular framework for streamlined evaluation of text. SentSpacecharacterizes textual input using diverse lexical, syntactic, and semantic features derivedfrom corpora and psycholinguistic experiments. Core sentence features fall into three primaryfeature spaces: 1) Lexical, 2) Contextual, and 3) Embeddings. To aid in the analysis of computed features, SentSpace provides a web interface for interactive visualization and comparison with text from large corpora. The modular design of SentSpace allows researchersto easily integrate their own feature computation into the pipeline while benefiting from acommon framework for evaluation and visualization. In this manuscript we will describe thedesign of SentSpace, its core feature spaces, and demonstrate an example use case by comparing human-written and machine-generated (GPT2-XL) sentences to each other. We findthat while GPT2-XL-generated text appears fluent at the surface level, psycholinguistic normsand measures of syntactic processing reveal key differences between text produced by humansand machines. Thus, SentSpace provides a broad set of cognitively motivated linguisticfeatures for evaluation of text within natural language processing, cognitive science, as wellas the social sciences.


CDRNN: Discovering Complex Dynamics in Human Language Processing
Cory Shain
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

The human mind is a dynamical system, yet many analysis techniques used to study it are limited in their ability to capture the complex dynamics that may characterize mental processes. This study proposes the continuous-time deconvolutional regressive neural network (CDRNN), a deep neural extension of continuous-time deconvolutional regression (Shain & Schuler, 2021) that jointly captures time-varying, non-linear, and delayed influences of predictors (e.g. word surprisal) on the response (e.g. reading time). Despite this flexibility, CDRNN is interpretable and able to illuminate patterns in human cognition that are otherwise difficult to study. Behavioral and fMRI experiments reveal detailed and plausible estimates of human language processing dynamics that generalize better than CDR and other baselines, supporting a potential role for CDRNN in studying human language processing.


Coreference information guides human expectations during natural reading
Evan Jaffe | Cory Shain | William Schuler
Proceedings of the 28th International Conference on Computational Linguistics

Models of human sentence processing effort tend to focus on costs associated with retrieving structures and discourse referents from memory (memory-based) and/or on costs associated with anticipating upcoming words and structures based on contextual cues (expectation-based) (Levy,2008). Although evidence suggests that expectation and memory may play separable roles in language comprehension (Levy et al., 2013), theories of coreference processing have largely focused on memory: how comprehenders identify likely referents of linguistic expressions. In this study, we hypothesize that coreference tracking also informs human expectations about upcoming words, and we test this hypothesis by evaluating the degree to which incremental surprisal measures generated by a novel coreference-aware semantic parser explain human response times in a naturalistic self-paced reading experiment. Results indicate (1) that coreference information indeed guides human expectations and (2) that coreference effects on memory retrieval may exist independently of coreference effects on expectations. Together, these findings suggest that the language processing system exploits coreference information both to retrieve referents from memory and to anticipate upcoming material.

Acquiring language from speech by learning to remember and predict
Cory Shain | Micha Elsner
Proceedings of the 24th Conference on Computational Natural Language Learning

Classical accounts of child language learning invoke memory limits as a pressure to discover sparse, language-like representations of speech, while more recent proposals stress the importance of prediction for language learning. In this study, we propose a broad-coverage unsupervised neural network model to test memory and prediction as sources of signal by which children might acquire language directly from the perceptual stream. Our model embodies several likely properties of real-time human cognition: it is strictly incremental, it encodes speech into hierarchically organized labeled segments, it allows interactive top-down and bottom-up information flow, it attempts to model its own sequence of latent representations, and its objective function only recruits local signals that are plausibly supported by human working memory capacity. We show that much phonemic structure is learnable from unlabeled speech on the basis of these local signals. We further show that remembering the past and predicting the future both contribute to the linguistic content of acquired representations, and that these contributions are at least partially complementary.


Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders
Cory Shain | Micha Elsner
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

In this paper, we deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages (Xitsonga and English). We show that the drive to model auditory percepts leads to latent clusters that partially align with theory-driven phonemic categories. We further evaluate the degree to which theory-driven phonological features are encoded in the latent bit patterns, finding that some (e.g. [+-approximant]), are well represented by the network in both languages, while others (e.g. [+-spread glottis]) are less so. Together, these findings suggest that many reliable cues to phonemic structure are immediately available to infants from bottom-up perceptual characteristics alone, but that these cues must eventually be supplemented by top-down lexical and phonotactic information to achieve adult-like phone discrimination. Our results also suggest differences in degree of perceptual availability between features, yielding testable predictions as to which features might depend more or less heavily on top-down cues during child language acquisition.

A large-scale study of the effects of word frequency and predictability in naturalistic reading
Cory Shain
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

A number of psycholinguistic studies have factorially manipulated words’ contextual predictabilities and corpus frequencies and shown separable effects of each on measures of human sentence processing, a pattern which has been used to support distinct mechanisms underlying prediction on the one hand and lexical retrieval on the other. This paper examines the generalizability of this finding to more realistic conditions of sentence processing by studying effects of frequency and predictability in three large-scale naturalistic reading corpora. Results show significant effects of word frequency and predictability in isolation but no effect of frequency over and above predictability, and thus do not provide evidence of distinct mechanisms. The non-replication of separable effects in a naturalistic setting raises doubts about the existence of such a distinction in everyday sentence comprehension. Instead, these results are consistent with previous claims that apparent effects of frequency are underlyingly effects of predictability.


pdf bib
Coreference and Focus in Reading Times
Evan Jaffe | Cory Shain | William Schuler
Proceedings of the 8th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2018)

Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects
Cory Shain | William Schuler
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Researchers in computational psycholinguistics frequently use linear models to study time series data generated by human subjects. However, time series may violate the assumptions of these models through temporal diffusion, where stimulus presentation has a lingering influence on the response as the rest of the experiment unfolds. This paper proposes a new statistical model that borrows from digital signal processing by recasting the predictors and response as convolutionally-related signals, using recent advances in machine learning to fit latent impulse response functions (IRFs) of arbitrary shape. A synthetic experiment shows successful recovery of true latent IRFs, and psycholinguistic experiments reveal plausible, replicable, and fine-grained estimates of latent temporal dynamics, with comparable or improved prediction quality to widely-used alternatives.


Breaking NLP: Using Morphosyntax, Semantics, Pragmatics and World Knowledge to Fool Sentiment Analysis Systems
Taylor Mahler | Willy Cheung | Micha Elsner | David King | Marie-Catherine de Marneffe | Cory Shain | Symon Stevens-Guille | Michael White
Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems

This paper describes our “breaker” submission to the 2017 EMNLP “Build It Break It” shared task on sentiment analysis. In order to cause the “builder” systems to make incorrect predictions, we edited items in the blind test data according to linguistically interpretable strategies that allow us to assess the ease with which the builder systems learn various components of linguistic structure. On the whole, our submitted pairs break all systems at a high rate (72.6%), indicating that sentiment analysis as an NLP task may still have a lot of ground to cover. Of the breaker strategies that we consider, we find our semantic and pragmatic manipulations to pose the most substantial difficulties for the builder systems.

Speech segmentation with a neural encoder model of working memory
Micha Elsner | Cory Shain
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present the first unsupervised LSTM speech segmenter as a cognitive model of the acquisition of words from unsegmented input. Cognitive biases toward phonological and syntactic predictability in speech are rooted in the limitations of human memory (Baddeley et al., 1998); compressed representations are easier to acquire and retain in memory. To model the biases introduced by these memory limitations, our system uses an LSTM-based encoder-decoder with a small number of hidden units, then searches for a segmentation that minimizes autoencoding loss. Linguistically meaningful segments (e.g. words) should share regular patterns of features that facilitate decoder performance in comparison to random segmentations, and we show that our learner discovers these patterns when trained on either phoneme sequences or raw acoustics. To our knowledge, ours is the first fully unsupervised system to be able to segment both symbolic and acoustic representations of speech.


Memory access during incremental sentence processing causes reading time latency
Cory Shain | Marten van Schijndel | Richard Futrell | Edward Gibson | William Schuler
Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC)

Studies on the role of memory as a predictor of reading time latencies (1) differ in their predictions about when memory effects should occur in processing and (2) have had mixed results, with strong positive effects emerging from isolated constructed stimuli and weak or even negative effects emerging from naturally-occurring stimuli. Our study addresses these concerns by comparing several implementations of prominent sentence processing theories on an exploratory corpus and evaluating the most successful of these on a confirmatory corpus, using a new self-paced reading corpus of seemingly natural narratives constructed to contain an unusually high proportion of memory-intensive constructions. We show highly significant and complementary broad-coverage latency effects both for predictors based on the Dependency Locality Theory and for predictors based on a left-corner parsing model of sentence processing. Our results indicate that memory access during sentence processing does take time, but suggest that stimuli requiring many memory access events may be necessary in order to observe the effect.

Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input
Cory Shain | William Bryce | Lifeng Jin | Victoria Krakovna | Finale Doshi-Velez | Timothy Miller | William Schuler | Lane Schwartz
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM). We deploy this algorithm to shed light on the extent to which human language learners can discover hierarchical syntax through distributional statistics alone, by modeling two widely-accepted features of human language acquisition and sentence processing that have not been simultaneously modeled by any existing grammar induction algorithm: (1) a left-corner parsing strategy and (2) limited working memory capacity. To model realistic input to human language learners, we evaluate our system on a corpus of child-directed speech rather than typical newswire corpora. Results beat or closely match those of three competing systems.